Capacity prediction method and system of energy storage equipment, medium and product

Abstract

The invention discloses a capacity prediction method and system of energy storage equipment, a medium and a product, and relates to the technical field of battery energy storage, and the method comprises the steps: obtaining the characteristic parameters of each battery unit in the energy storage equipment; inputting the average discharge voltage, the average discharge current and the accumulated charge-discharge cycle times into a preset battery capacity calculation formula to obtain the current capacity of each battery unit; determining the capacity of the energy storage equipment according to the battery topological structure of the energy storage equipment; based on the current environment temperature and the preset standard environment temperature, the capacity of the energy storage equipment is corrected through a preset temperature correction coefficient, and the current capacity of the energy storage equipment is obtained; and according to the current capacity and the historical capacity attenuation trend of the energy storage equipment, predicting the residual capacity of the energy storage equipment when the preset charge-discharge cycle number is reached in the future. By implementing the method, the capacity prediction accuracy of the energy storage equipment can be improved.

Description

Technical Field

[0001] The present application relates to the field of battery energy storage technology, and in particular to a capacity prediction method, system, medium and product for energy storage equipment. Background Art

[0002] Energy storage devices, especially battery energy storage systems, play a vital role in modern energy management. As the use time increases, energy storage devices will undergo an irreversible aging process, which directly affects their performance and economic value. Effective battery status monitoring and life prediction can not only help timely diagnosis and take corresponding maintenance strategies, but also determine the best replacement time, thereby significantly improving the use value of the battery and extending its service life.

[0003] At present, relevant technologies have established a relatively complete battery management system and data monitoring platform, which can monitor and manage the battery usage status in real time through battery modeling and data analysis.

[0004] Although current technologies provide certain battery status monitoring and prediction capabilities, since energy storage devices often involve the integration of multiple battery cells, capacity prediction becomes complex and unreliable. Summary of the invention

[0005] The present application provides a capacity prediction method, system, medium and product for energy storage equipment, which are used to improve the accuracy of capacity prediction of energy storage equipment.

[0006] In a first aspect, the present application provides a method for predicting the capacity of an energy storage device, which is applied to an energy storage management system, the method comprising: obtaining characteristic parameters of each battery cell in the energy storage device, the characteristic parameters comprising an average discharge voltage, an average discharge current, and a cumulative number of charge and discharge cycles; inputting the average discharge voltage, the average discharge current, and the cumulative number of charge and discharge cycles into a preset battery capacity calculation formula to obtain the current capacity of each battery cell; determining the capacity of the energy storage device according to a battery topology structure of the energy storage device, the battery topology structure being used to represent a series, parallel, or series-parallel mixed connection relationship between the battery cells; based on a current ambient temperature and a preset standard ambient temperature, correcting the capacity of the energy storage device by a preset temperature correction coefficient to obtain the current capacity of the energy storage device; and predicting the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future according to the current capacity of the energy storage device and a historical capacity decay trend.

[0007] By adopting the above technical solution, first, the energy storage management system obtains the characteristic parameters of each battery cell, calculates the current capacity of the battery cell using the preset battery capacity calculation formula, and refines the capacity of the energy storage device into the capacity of a single battery cell. Next, the energy storage management system determines the overall capacity of the energy storage device in combination with the battery topology. Since the temperature may affect the capacity of the energy storage device, the energy storage management system needs to perform temperature correction to obtain a more accurate current capacity of the energy storage device. Finally, the energy storage management system predicts the remaining capacity of the energy storage device when the preset number of charge and discharge cycles is reached in the future, thereby achieving a comprehensive assessment of the capacity of the energy storage device. This method takes into account the influence of single cell characteristics, battery topology and environmental factors, and is more accurate and reliable than directly using system-level data. At the same time, by predicting future capacity, it provides a basis for equipment maintenance and replacement, which helps to extend the service life of energy storage equipment and improve its economic value.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the preset battery capacity calculation formula is: C = C 0 *(1-K 1 *NK 2 *|I|-K 3 *|U|) formula, C represents the current capacity of each battery cell, C 0 represents the initial capacity, K 1 represents the impact factor of the cumulative charge and discharge cycle number, N represents the cumulative charge and discharge cycle number, K 2 Indicates the influence factor of discharge current, I represents the average discharge current, K 3 represents the influence factor of the discharge voltage, and U represents the average discharge voltage.

[0009] By adopting the above technical solution, the preset battery capacity calculation formula takes into account the impact of three key factors on battery capacity: the cumulative number of charge and discharge cycles, discharge current and discharge voltage. By introducing the corresponding influencing factors, the accurate quantification of the capacity decay process of the single battery is achieved. This method not only takes into account the impact of the number of battery uses on life, but also incorporates the impact of usage intensity (current) and usage depth (voltage), thereby more comprehensively reflecting the actual usage status of the battery. Through this refined calculation, the current state of each battery cell can be more accurately evaluated, laying a solid foundation for subsequent system-level capacity calculation and prediction.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the capacity of the energy storage device is determined according to the battery topology structure of the energy storage device, and the battery topology structure is used to represent the series, parallel or series-parallel mixed connection relationship between the battery cells, specifically including: determining the series, parallel or series-parallel mixed connection relationship of each battery cell according to the battery topology structure of the energy storage device; according to the battery cells in the parallel connection relationship, adding the current capacity of each battery cell in the parallel branch as the capacity of the parallel branch; according to the battery cells in the series connection relationship, determining the battery cell with the smallest current capacity in the series branch as the capacity of the series branch; and calculating the capacity of the energy storage device based on the capacity of each branch and the series-parallel mixed connection relationship.

[0011] By adopting the above technical solution, the energy storage management system takes into account the series, parallel or mixed series-parallel connection relationship between battery cells through the battery topology of the energy storage device, and realizes accurate calculation from the capacity of a single battery to the capacity of the entire energy storage device. The advantage of this method is that it fully considers the impact of different connection methods on the capacity of the energy storage device: the parallel connection increases the total capacity by superimposing the capacity, while the series connection is limited by the weakest link. Through this meticulous analysis and calculation, the actual capacity status of the entire energy storage device can be accurately reflected, avoiding the errors that may be caused by simple addition or averaging, which not only improves the accuracy of capacity prediction, but also provides an important basis for optimizing design and maintenance strategies, thereby improving the performance and reliability of the entire energy storage device.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future is predicted based on the current capacity and the historical capacity decay trend of the energy storage device, specifically including: determining the historical capacity decay trend based on the initial capacity, current capacity and cumulative number of charge and discharge cycles of the energy storage device; inputting the preset number of charge and discharge cycles, the current capacity of the energy storage device and the historical capacity decay trend into a preset energy storage device capacity prediction formula to obtain the remaining capacity of the energy storage device.

[0013] By adopting the above technical solution, the energy storage management system determines the historical capacity decay trend based on the initial capacity, current capacity and cumulative charge and discharge cycle number of the energy storage device, and combines this historical capacity decay trend with the preset charge and discharge cycle number and current capacity to predict the remaining capacity of the energy storage device in the future. The advantage of this method is that it not only takes into account the current state, but also incorporates the historical capacity decay trend, making the prediction more accurate and reliable. At the same time, it also greatly improves the scientific nature and foresight of energy storage equipment management, which helps to improve the economic benefits and operational reliability of the entire energy storage equipment.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of predicting the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future based on the current capacity and the historical capacity decay trend of the energy storage device, the method further includes: calculating the actual capacity of the energy storage device when the preset number of charge and discharge cycles is reached in the future; and correcting the historical capacity decay trend based on the actual capacity of the energy storage device and the remaining capacity of the energy storage device.

[0015] By adopting the above technical solution, by comparing the predicted remaining capacity with the actual capacity when the preset number of charge and discharge cycles is reached, a dynamic correction of the historical capacity decay trend is achieved, the accuracy of long-term predictions is improved, and a more reliable decision-making basis can be provided for the energy storage management system, which is conducive to optimizing the full life cycle management strategy of energy storage equipment.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of obtaining characteristic parameters of each battery cell in the energy storage device, wherein the characteristic parameters include an average discharge voltage, an average discharge current, and a cumulative number of charge and discharge cycles, the method further includes: inputting the average discharge voltage and the average discharge current of the battery cell into a preset battery abnormality recognition model to obtain a recognition result; when the recognition result is an abnormal behavior, issuing a battery abnormality warning.

[0017] By adopting the above technical solution, the method realizes timely detection and early warning of abnormal battery status by real-time monitoring of the average discharge voltage and average discharge voltage of the battery cells and inputting these data into the preset battery abnormality recognition model. The advantage of this active monitoring and early warning mechanism is that it can detect potential battery problems in time to avoid serious failures, reduce safety risks, and reduce maintenance costs and downtime.

[0018] In combination with some embodiments of the first aspect, in some embodiments, before the step of inputting the average discharge voltage and the average discharge current of the battery cell into a preset battery abnormality recognition model to obtain an identification result, the method also includes: obtaining historical discharge data of the battery cell, the historical discharge data including historical discharge voltage and historical discharge current; marking the historical discharge data to obtain normal data and abnormal data, the abnormal data being the historical discharge voltage and the historical discharge current corresponding to when the battery cell exhibits abnormal behavior, and the normal data being the data other than the abnormal data in the historical discharge data of the battery cell; dividing the historical discharge data into a training set and a test set; using the training set to train the preset model, and using the test set to evaluate the trained preset model; when it is determined that the accuracy of the preset model reaches a preset accuracy threshold, obtaining the preset battery abnormality recognition model.

[0019] By adopting the above technical solution, the training process of the preset battery anomaly recognition model is described in detail, including steps such as data acquisition, labeling, division, training and evaluation. By using the historical discharge data of real battery cells, including normal data and abnormal data, the preset model can learn the behavioral characteristics of battery cells in various states. The practice of dividing the training set and the test set ensures the generalization ability of the preset model, while the preset accuracy threshold ensures the reliability of the preset model. This method not only improves the accuracy of anomaly detection, but also has strong adaptability and scalability.

[0020] In a second aspect, an embodiment of the present application provides an energy storage management system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the energy storage management system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, and when the above-mentioned computer program product runs on an energy storage management system, the above-mentioned energy storage management system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on an energy storage management system, enables the energy storage management system to execute the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the energy storage management system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of a multi-level capacity prediction method from single battery units to the overall energy storage device, the present invention can comprehensively and accurately evaluate and predict the capacity status of the energy storage device, effectively solving the problems of insufficient accuracy and low reliability caused by relying solely on system-level data for prediction in related technologies, thereby achieving high accuracy, high reliability and high adaptability in energy storage device capacity prediction.

[0025] 2. Due to the adoption of an intelligent prediction method combining dynamic self-correction and anomaly detection, the present invention can continuously optimize the capacity prediction method and identify potential risks in a timely manner, effectively solving the problems of poor adaptability and inability to detect anomalies in a timely manner caused by the solidification of capacity prediction methods in related technologies, thereby realizing the intelligence and predictability of energy storage equipment management.

[0026] 3. Since a comprehensive evaluation method that considers the influence of multiple factors is adopted, the present invention can comprehensively reflect the actual usage status and performance changes of energy storage equipment, effectively solving the prediction deviation problem caused by ignoring environmental factors and usage pattern differences in related technologies, thereby achieving more accurate and personalized capacity prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for predicting the capacity of an energy storage device in an embodiment of the present application; Figure 2 is another flow chart of the method for predicting the capacity of an energy storage device in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the energy storage management system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] The following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of a method for predicting the capacity of an energy storage device in an embodiment of the present application.

[0031] S101, obtaining characteristic parameters of each battery cell in the energy storage device, the characteristic parameters including average discharge voltage, average discharge current and cumulative number of charge and discharge cycles; Among them, the energy storage management system refers to an intelligent system used to monitor, control and optimize the operation of energy storage equipment. Energy storage equipment refers to equipment used to store electrical energy and release it when needed, such as battery packs or supercapacitors. Battery cells refer to the basic energy storage units in energy storage equipment, usually single batteries. Characteristic parameters are used to represent key indicators of the current state and usage history of battery cells. The average discharge voltage represents the average voltage value of the battery cell during the discharge process. The average discharge current refers to the average current value of the battery cell during the discharge process. The cumulative number of charge and discharge cycles is used to indicate the total number of charge and discharge cycles that the battery cell has completed.

[0032] The energy storage management system continuously performs this step during the operation of the energy storage device to monitor the status of each battery cell in real time. Specifically, first, the energy storage management system collects the voltage data and current data of each battery cell in real time through a built-in or external sensor network. Then, the energy storage management system processes the collected voltage data and current data of each battery cell, and calculates the average discharge voltage and average discharge current within a certain period of time (such as 15 minutes or 1 hour). At the same time, the energy storage management system records the charge and discharge process of each battery cell. When a complete charge and discharge cycle is completed, the cumulative number of charge and discharge cycles is increased by 1. These characteristic parameters are stored in the database of the energy storage management system to provide basic data support for subsequent capacity calculations and predictions.

[0033] S102, inputting the average discharge voltage, the average discharge current and the accumulated number of charge and discharge cycles into a preset battery capacity calculation formula to obtain the current capacity of each battery cell; The preset battery capacity calculation formula refers to a mathematical model used to calculate the current capacity of a battery cell. The current capacity represents the amount of electrical energy that a battery cell can store and release in its current state. The preset battery capacity calculation formula is: C=C 0 *(1-K 1 *NK 2 *|I|-K 3 *|U|) In the formula, C represents the current capacity of each battery cell, C 0 represents the initial capacity, K 1 represents the impact factor of the cumulative charge and discharge cycle number, N represents the cumulative charge and discharge cycle number, K 2 Indicates the influence factor of discharge current, I represents the average discharge current, K 3 represents the influence factor of the discharge voltage, and U represents the average discharge voltage.

[0034] After obtaining the characteristic parameters of each battery cell, the energy storage management system immediately executes this step to evaluate the current capacity of each battery cell. Specifically, first, the energy storage management system calls the preset battery capacity calculation formula. The preset battery capacity calculation formula usually takes into account the impact of battery aging, usage intensity (current) and usage depth (voltage) on the capacity of the battery cell. The energy storage management system substitutes the average discharge voltage, average discharge current and cumulative number of charge and discharge cycles obtained in step S101 into the preset battery capacity calculation formula for numerical calculation. The calculation result is the current capacity of the battery cell. The energy storage management system repeats this calculation process for each battery cell, and finally obtains the current capacity of all battery cells in the energy storage device.

[0035] S103, determining the capacity of the energy storage device according to the battery topology structure of the energy storage device, where the battery topology structure is used to represent the series, parallel or series-parallel mixed connection relationship between the battery cells; Among them, battery topology refers to the connection method and arrangement of battery cells in energy storage devices. Series connection means that the battery cells are connected end to end and the voltage is accumulated. Parallel connection means that the positive poles of the battery cells are connected and the negative poles are connected, and the capacities are superimposed. A series-parallel mixed connection relationship means a complex connection method with both series and parallel connections. The capacity of the energy storage device is used to indicate the total amount of electrical energy that the entire energy storage device can store and release.

[0036] After calculating the current capacity of each battery cell, the energy storage management system immediately performs this step to evaluate the capacity of the energy storage device. Specifically, first, the energy storage management system reads the pre-stored battery topology of the energy storage device, which describes in detail the connection relationship between the battery cells. For battery cells connected in parallel, the energy storage management system directly adds their current capacities as the effective capacity of the parallel branch. For battery cells connected in series, the energy storage management system selects the battery cell with the smallest current capacity as the effective capacity of the series branch. For complex series-parallel mixed connections, the energy storage management system first calculates the capacity of each parallel branch, and then determines the final capacity according to the series connection rules. After considering all connection relationships, the energy storage management system finally obtains the capacity of the energy storage device, which reflects the current performance status of the energy storage device and provides an important basis for subsequent capacity prediction and management decisions.

[0037] S104, based on the current ambient temperature and the preset standard ambient temperature, the capacity of the energy storage device is corrected by a preset temperature correction coefficient to obtain the current capacity of the energy storage device; The current ambient temperature refers to the actual temperature environment in which the energy storage device is currently located. The preset standard ambient temperature represents the reference temperature for battery performance testing and specification definition, usually 25°C. The preset temperature correction coefficient is used to represent the correction factor for the effect of temperature change on battery capacity. The current capacity of the energy storage device refers to the effective capacity of the energy storage device at the actual ambient temperature after temperature correction.

[0038] After determining the capacity of the energy storage device, the energy storage management system immediately performs this step to consider the impact of the actual ambient temperature on the capacity of the energy storage device. Specifically, first, the energy storage management system obtains the current ambient temperature of the energy storage device through the temperature sensor. Then, the energy storage management system calls the preset standard ambient temperature and the preset temperature correction coefficient. The energy storage management system can obtain the current capacity of the energy storage device after correction based on the current ambient temperature, the preset standard ambient temperature, and the preset temperature correction coefficient. An example is given below: Assume that the energy storage device capacity obtained in step S103 is 94.9Ah; The preset temperature correction coefficient is 0.998 / °C. This preset temperature correction coefficient means that for every 1°C deviation from the standard temperature, the capacity of the energy storage device will change by 0.2% (1-0.998=0.002, i.e. 0.2%). The preset standard ambient temperature is 25°C, which represents the ideal operating temperature of the energy storage device; The current ambient temperature is 30℃; The temperature difference is 30℃-25℃=5℃; The current ambient temperature is 5°C higher than the preset standard ambient temperature.

[0039] Capacity correction calculation: Capacity change ratio caused by temperature: 5℃*0.002=0.01 (i.e. 1%); The current capacity of the corrected energy storage device is: 94.9Ah*(1-0.01)=94.9Ah*0.99=94.05Ah The method listed above is a simplified linear approximation. In practical applications, the effect of ambient temperature on battery capacity may be more complex and may require the use of a nonlinear model or a lookup table for more accurate correction, which is not limited here.

[0040] S105. Predict the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future based on the current capacity and historical capacity attenuation trend of the energy storage device.

[0041] The historical capacity decay trend refers to the law that the capacity of the energy storage device decreases over time or the number of charge and discharge times during past use. The preset number of charge and discharge cycles refers to the number of charge and discharge cycles at a certain point in the future set by the user. The remaining capacity is used to indicate the capacity level that the energy storage device can still maintain when the preset number of charge and discharge cycles is reached.

[0042] After obtaining the current capacity of the energy storage device, the energy storage management system performs this step to evaluate the future performance of the energy storage device. Specifically, first, the energy storage management system extracts the historical capacity data of the energy storage device from the database. The historical capacity data includes the capacity values ​​at different time points or charge and discharge cycles. The energy storage management system uses these historical capacity data, combined with the current capacity of the energy storage device, to fit a capacity decay curve through a mathematical model (such as an exponential decay model or a machine learning algorithm). This capacity decay curve describes how the capacity decreases as the number of charge and discharge cycles increases. Then, the energy storage management system substitutes the preset number of charge and discharge cycles into this capacity decay curve and calculates the remaining capacity under the preset number of charge and discharge cycles. For example, if the preset number of charge and discharge cycles is 5000, the energy storage management system will calculate the remaining capacity of the energy storage device after completing 5000 charge and discharge cycles. This prediction result can help users evaluate the remaining service life of energy storage equipment and provide an important basis for equipment maintenance and replacement decisions.

[0043] By adopting the above technical solution, first, the energy storage management system obtains the characteristic parameters of each battery cell, calculates the current capacity of the battery cell using the preset battery capacity calculation formula, and refines the capacity of the energy storage device into the capacity of a single battery cell. Next, the energy storage management system determines the overall capacity of the energy storage device in combination with the battery topology. Since the temperature may affect the capacity of the energy storage device, the energy storage management system needs to perform temperature correction to obtain a more accurate current capacity of the energy storage device. Finally, the energy storage management system predicts the remaining capacity of the energy storage device when the preset number of charge and discharge cycles is reached in the future, thereby achieving a comprehensive assessment of the capacity of the energy storage device. This method takes into account the influence of single cell characteristics, battery topology and environmental factors, and is more accurate and reliable than directly using system-level data. At the same time, by predicting future capacity, it provides a basis for equipment maintenance and replacement, which helps to extend the service life of energy storage equipment and improve its economic value.

[0044] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the capacity prediction method of the energy storage device in the embodiment of the present application.

[0045] S201, obtaining characteristic parameters of each battery cell in the energy storage device, the characteristic parameters including average discharge voltage, average discharge current and cumulative number of charge and discharge cycles; For details, please refer to step S101, which will not be described in detail here.

[0046] S202, obtaining historical discharge data of the battery cell, wherein the historical discharge data includes a historical discharge voltage and a historical discharge current; annotating the historical discharge data to obtain normal data and abnormal data, wherein the abnormal data is the historical discharge voltage and the historical discharge current corresponding to the abnormal behavior of the battery cell, and the normal data is the data other than the abnormal data in the historical discharge data of the battery cell; dividing the historical discharge data into a training set and a test set; using the training set to train a preset model, and using the test set to evaluate the trained preset model; when it is determined that the accuracy of the preset model reaches a preset accuracy threshold, obtaining the preset battery abnormality recognition model.

[0047] The steps to build a preset battery anomaly recognition model based on deep learning are as follows: First, the energy storage management system collects historical discharge data of multiple battery cells within a preset period of time in the past (for example, within 6 months), including historical discharge voltage and historical discharge current, and the energy storage management system records the behavior of each battery cell under the historical discharge voltage and historical discharge current, and marks the historical discharge voltage and historical discharge current corresponding to the abnormal behavior of the battery cell as abnormal data, and marks the historical discharge data other than the abnormal data as normal data. The determination of the normal behavior or abnormal behavior of each battery cell under the historical discharge voltage and historical discharge current can be obtained through historical maintenance records or expert evaluation, which is not limited here. The energy storage management system stores the collected historical discharge voltage and historical discharge current as well as normal behavior or abnormal behavior in the data set D, and the format of each data is (historical discharge voltage, historical discharge current, normal behavior) or (historical discharge voltage, historical discharge current, abnormal behavior). Among them, the historical discharge voltage and historical discharge current are the input features of the model training, and the normal behavior or abnormal behavior is the output feature of the model training.

[0048] Then, the energy storage management system constructs a LSTM-based recurrent neural network, which includes an input layer, two LSTM hidden layers, a fully connected layer, and an output layer. The input layer inputs the historical discharge voltage and the historical discharge current, the number of nodes in the hidden layer is set to 64, the number of nodes in the fully connected layer is set to 32, and the output layer outputs normal behavior or abnormal behavior.

[0049] Next, the energy storage management system uses the Adam optimizer, the learning rate is set to 0.001, and the training batch size is 32. It can also be set according to the actual situation and is not limited here. 80% of the historical data is divided into a training set and 20% is divided into a validation set. 100 epochs are trained and the model with the highest accuracy of the validation set is saved. It can also be set according to the actual situation and is not limited here. Epoch is the process in which the training data set passes through the neural network once. In machine learning and deep learning, epoch is a unit used to measure the number of times the entire training set is repeatedly learned. Specifically, when the neural network completes a forward calculation and back propagation process, that is, all data has been processed by the network once, an epoch is completed. The energy storage management system uses binary cross entropy as the loss function and Early Stopping to prevent overfitting. When the value of the loss function exceeds the preset function threshold, the model training is determined to be completed and the preset battery abnormality recognition model is obtained. Early Stopping is a technology in deep learning and machine learning to prevent model overfitting. It determines when to stop training by monitoring the performance of the model on the validation set.

[0050] Finally, the energy storage management system inputs the input features in the validation set into the preset battery anomaly recognition model, and then obtains the predicted output of the preset battery anomaly recognition model, compares the predicted output of the preset battery anomaly recognition model with the actual output features in the validation set, and uses some performance indicators such as accuracy, precision, recall, F1 score, mean square error (MSE), etc. to evaluate the performance of the preset battery anomaly recognition model. According to the performance of the preset battery anomaly recognition model on the validation set, adjust the parameters of the preset battery anomaly recognition model, including adjusting the learning rate, changing the model complexity (such as increasing or decreasing the number of layers or nodes of the neural network), modifying the regularization strength, etc. This process may require multiple iterations, each adjustment based on the previous learning results, so as to optimize the preset battery anomaly recognition model.

[0051] S203, inputting the average discharge voltage and average discharge current of the battery cell into a preset battery abnormality recognition model to obtain a recognition result; The energy storage management system inputs the average discharge voltage and average discharge current of the battery cell obtained in step S201 into the preset battery abnormality recognition model trained in step S202 to obtain the behavior determination result of the battery cell. S204, when the recognition result is abnormal behavior, issuing a battery abnormality warning; If the identification result is abnormal behavior, it means that the battery cell may have some problems or abnormal conditions, or the performance of the battery cell has seriously degraded, or the battery cell may have safety hazards that require attention. The energy storage management system issues a battery abnormality warning to prompt the user.

[0052] S205, inputting the average discharge voltage, the average discharge current and the accumulated number of charge and discharge cycles into a preset battery capacity calculation formula to obtain the current capacity of each battery cell; For details, please refer to step S102, which will not be described in detail here.

[0053] S206, determining the series, parallel or series-parallel mixed connection relationship of each battery unit according to the battery topology structure of the energy storage device; The energy storage management system first reads the pre-stored battery topology of the energy storage device. The battery topology is usually represented in the form of a graph or matrix, which describes in detail the location and connection method of each battery cell. The energy storage management system uses a special topology analysis algorithm to parse this structural information and identify pure series branches, pure parallel branches, and complex branches containing multiple layers of series and parallel connections. For each branch, the energy storage management system determines the battery cell numbers contained therein and their connection relationships.

[0054] S207, according to the battery units in parallel connection relationship, adding the current capacities of the battery units in the parallel branch as the capacity of the parallel branch; The parallel branch refers to a circuit branch formed by connecting multiple battery cells in parallel. The capacity of the parallel branch is used to represent the total electrical energy storage capacity of the parallel branch.

[0055] After determining the battery topology, the energy storage management system immediately performs this step to calculate the capacity of the parallel branch. Specifically, the energy storage management system identifies all parallel branches, and for each parallel branch, retrieves the current capacity of all battery cells contained in the parallel branch from the database. The energy storage management system uses a simple addition operation to add up the current capacity of all battery cells in the parallel branch. For example, if a parallel branch contains three battery cells, and their current capacities are 100Ah, 95Ah, and 98Ah, respectively, then the total capacity of the parallel branch is 293Ah. The energy storage management system repeats this calculation process for each parallel branch and temporarily stores the results for subsequent series-parallel mixed calculations.

[0056] S208, according to the battery cells in the series connection relationship, determining the battery cell with the smallest current capacity in the series branch as the capacity of the series branch; The series branch refers to a circuit branch formed by connecting multiple battery cells in series. The capacity of the series branch is used to represent the effective electric energy storage capacity of the series branch.

[0057] After calculating the capacity of the parallel branch, the energy storage management system immediately performs this step to evaluate the capacity of the series branch. Specifically, the energy storage management system identifies all series branches, and for each series branch, extracts the current capacity of all battery cells contained in the series branch from the database. The energy storage management system uses a comparison algorithm to traverse the current capacity of all battery cells in the series branch and find the minimum value. For example, if a series branch contains four battery cells, and their current capacities are 100Ah, 98Ah, 102Ah, and 97Ah, respectively, then the effective capacity of the series branch is determined to be 97Ah. The energy storage management system repeats this process for each series branch and temporarily stores the results.

[0058] S209, calculating the capacity of the energy storage device based on the capacity of each branch and the series-parallel mixed connection relationship; Among them, the branch represents the series branch or parallel branch in the energy storage device. The series-parallel hybrid connection relationship is used to describe the complex battery unit connection method in the energy storage device, including multiple levels of series and parallel combinations. The capacity of the energy storage device refers to the total amount of electrical energy that the entire energy storage device can store and release.

[0059] After calculating the capacity of all series branches and parallel branches, the energy storage management system immediately executes this step to obtain the capacity of the energy storage device. Specifically, the energy storage management system calculates the capacity layer by layer outward, starting from the innermost branch, according to the battery topology determined in step S206. For parallel branches, the energy storage management system directly adds the current capacity of the battery cells. For series branches, the energy storage management system selects the value with the smallest current capacity in the battery cell. When dealing with complex multi-level series and parallel combinations, the energy storage management system may use a recursive algorithm or a hierarchical calculation method. For example, for a structure such as "(A1||A2)-(B1||B2)-C" (where "-" represents series connection and "||" represents parallel connection), the energy storage management system will first calculate the parallel capacity of A1||A2 and B1||B2, and then calculate these two results in series with C, and select the minimum value of the three as the final capacity, that is, the capacity of the energy storage device.

[0060] S210, based on the current ambient temperature and the preset standard ambient temperature, the capacity of the energy storage device is corrected by a preset temperature correction coefficient to obtain the current capacity of the energy storage device; For details, please refer to step S104, which will not be described in detail here.

[0061] S211, determining the historical capacity decay trend according to the initial capacity, current capacity and cumulative number of charge and discharge cycles of the energy storage device; Among them, initial capacity refers to the rated capacity of the energy storage device in a brand new state, usually the nominal capacity of the energy storage device when it leaves the factory. Current capacity refers to the actual available capacity of the energy storage device at the current point in time. The cumulative number of charge and discharge cycles is used to indicate the total number of charge and discharge cycles that the energy storage device has completed. The historical capacity decay trend refers to the law that the capacity of the energy storage device decreases with the use time or the number of charge and discharge times.

[0062] The energy storage management system performs this step after obtaining the current capacity of the energy storage device. Specifically, the energy storage management system calculates the capacity decay rate by comparing the initial capacity and current capacity of the energy storage device. Next, the energy storage management system associates this capacity decay rate with the cumulative number of charge and discharge cycles, and uses a mathematical model (such as linear regression, exponential decay model, or more complex machine learning algorithm) to fit a historical capacity decay curve. This historical capacity decay curve describes how the capacity decreases with the increase in the number of charge and discharge cycles. For example, if it is found that the capacity decreases by 5% for every 1,000 charge and discharge cycles, the energy storage management system can establish a simple linear model, and other implementation methods are not limited here.

[0063] Here is an example: assuming that the initial capacity of the energy storage device is 100Ah, and the cumulative number of charge and discharge cycles is 0; the initial capacity of the energy storage device is 94.05Ah (after correction for environmental factors), and the cumulative number of charge and discharge cycles is 500; capacity decay rate = (initial capacity - current capacity) / cumulative number of charge and discharge cycles = (100Ah - 94.05Ah) / 500 = 0.0119Ah / number of charge and discharge cycles. The energy storage management system can determine that 0.0119Ah / number of charge and discharge cycles is the historical capacity decay trend.

[0064] S212, inputting the preset number of charge and discharge cycles, the current capacity of the energy storage device, and the historical capacity decay trend into a preset energy storage device capacity prediction formula to obtain the remaining capacity of the energy storage device; The energy storage management system calls a preset energy storage device capacity prediction formula, inputs the preset number of charge and discharge cycles, the current capacity of the energy storage device and the historical capacity decay trend into the preset energy storage device capacity prediction formula, and obtains the remaining capacity of the energy storage device.

[0065] Following the example of step S211, assuming that the remaining capacity of the energy storage device after 100 charge and discharge cycles is to be predicted, that is, the number of cycles = 600, the remaining capacity of the energy storage device is calculated using linear extrapolation: Remaining capacity = current capacity - (capacity decay rate * additional number of cycles) = 94.05 Ah - (0.0119 Ah / cycle * 100 cycles) = 94.05 Ah - 1.19 Ah = 92.86 Ah.

[0066] S213, when the preset number of charge and discharge cycles is reached in the future, calculating the actual capacity of the energy storage device; The energy storage management system executes this step when the energy storage device actually reaches the preset number of charge and discharge cycles in the future to verify the accuracy of the previous prediction. Specifically, the energy storage management system confirms whether the energy storage device will reach the preset number of charge and discharge cycles in the future. If so, the energy storage management system calculates the actual capacity of the energy storage device through steps S101 to S104.

[0067] S214: Correct the historical capacity decay trend according to the actual capacity of the energy storage device and the remaining capacity of the energy storage device.

[0068] After obtaining the actual capacity of the energy storage device, the energy storage management system immediately performs this step to improve the accuracy of future predictions. Specifically, the energy storage management system first compares the actual capacity of the energy storage device and the remaining capacity of the energy storage device to calculate the prediction error. For example, if the predicted remaining capacity is 80% of the initial capacity, and the actual measurement result is 85%, there is a 5% positive error. The energy storage management system then analyzes the possible causes of this error, such as environmental factors, changes in usage patterns, or inaccuracies in the initial model. Based on this analysis, the energy storage management system adjusts the historical capacity decay trend. If a linear model is used, the slope may be adjusted; if it is an exponential model, the decay coefficient may be modified. In more complex machine learning models, the energy storage management system may retrain the model to take new data points into account.

[0069] In implementing this method, since a multi-level capacity prediction method from single battery units to the overall energy storage device is adopted, the present invention can comprehensively and accurately evaluate and predict the capacity status of the energy storage device, effectively solving the problem of insufficient accuracy and low reliability caused by relying solely on system-level data for prediction in related technologies, thereby achieving high accuracy, high reliability and high adaptability in the capacity prediction of energy storage devices. Since an intelligent prediction method combining dynamic self-correction and anomaly detection is adopted, the present invention can continuously optimize the capacity prediction method and timely identify potential risks, effectively solving the problem of poor adaptability and inability to detect anomalies in time caused by the solidification of capacity prediction methods in related technologies, thereby achieving intelligent and predictable management of energy storage devices. Since a comprehensive evaluation method that considers the influence of multiple factors is adopted, the present invention can comprehensively reflect the actual usage status and performance changes of energy storage equipment, effectively solving the problem of prediction deviation caused by ignoring environmental factors and usage pattern differences in related technologies, thereby achieving more accurate and personalized capacity prediction.

[0070] The energy storage management system in the embodiment of the present invention is described below from the perspective of hardware processing. Figure 3, is a schematic diagram of a physical device structure of an energy storage management system in an embodiment of the present application.

[0071] It should be noted that Figure 3 The structure of the energy storage management system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0072] like Figure 3 As shown, the energy storage management system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0073] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0074] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0075] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0077] Specifically, the energy storage management system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the capacity prediction method of the energy storage device provided in the above embodiment is implemented.

[0078] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the energy storage management system described in the above embodiment; or may exist independently without being assembled into the energy storage management system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the energy storage management system, the energy storage management system implements the capacity prediction method of the energy storage device provided in the above embodiment.

[0079] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0080] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0081] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A capacity prediction method for energy storage equipment, characterized in that: Applied to an energy storage management system, the method comprises: Acquire characteristic parameters of each battery cell in the energy storage device, wherein the characteristic parameters include average discharge voltage, average discharge current and cumulative number of charge and discharge cycles; Inputting the average discharge voltage, the average discharge current and the accumulated number of charge and discharge cycles into a preset battery capacity calculation formula to obtain the current capacity of each battery cell; Determine the capacity of the energy storage device according to the battery topology of the energy storage device, wherein the battery topology is used to represent the series, parallel or series-parallel mixed connection relationship between the battery cells; Based on the current ambient temperature and the preset standard ambient temperature, the capacity of the energy storage device is corrected by a preset temperature correction coefficient to obtain the current capacity of the energy storage device; Based on the current capacity and historical capacity decay trend of the energy storage device, the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future is predicted.

2. The method according to claim 1, characterized in that The preset battery capacity calculation formula is: C=C0*(1-K1*N-K2*|I|-K3*|U|) In the formula, C represents the current capacity of each battery cell, C0 represents the initial capacity, K1 represents the influencing factor of the cumulative number of charge and discharge cycles, N represents the cumulative number of charge and discharge cycles, K2 represents the influencing factor of the discharge current, I represents the average discharge current, K3 represents the influencing factor of the discharge voltage, and U represents the average discharge voltage.

3. The method according to claim 1, characterized in that The energy storage device capacity is determined according to the battery topology of the energy storage device, wherein the battery topology is used to represent the series, parallel or series-parallel mixed connection relationship between the battery cells, and specifically includes: Determine the series, parallel or series-parallel mixed connection relationship of each battery unit according to the battery topology structure of the energy storage device; According to the battery cells in parallel connection relationship, the current capacities of the battery cells in the parallel branch are added as the capacity of the parallel branch; According to the battery cells in the series connection relationship, determining the battery cell with the smallest current capacity in the series branch as the capacity of the series branch; The capacity of the energy storage device is calculated based on the capacity of each branch and the series-parallel mixed connection relationship.

4. The method according to claim 1, characterized in that: The predicting, based on the current capacity and historical capacity attenuation trend of the energy storage device, of the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future specifically includes: Determine the historical capacity decay trend according to the initial capacity, current capacity and accumulated number of charge and discharge cycles of the energy storage device; The preset number of charge and discharge cycles, the current capacity of the energy storage device and the historical capacity decay trend are input into a preset energy storage device capacity prediction formula to obtain the remaining capacity of the energy storage device.

5. The method according to claim 4, characterized in that After the step of predicting the remaining capacity of the energy storage device when a preset number of charge and discharge cycles is reached in the future based on the current capacity and historical capacity attenuation trend of the energy storage device, the method further includes: When the preset number of charge and discharge cycles is reached in the future, calculating the actual capacity of the energy storage device; The historical capacity decay trend is corrected according to the actual capacity of the energy storage device and the remaining capacity of the energy storage device.

6. The method according to claim 1, characterized in that After the step of obtaining characteristic parameters of each battery cell in the energy storage device, wherein the characteristic parameters include an average discharge voltage, an average discharge current, and a cumulative number of charge and discharge cycles, the method further includes: The average discharge voltage and average discharge current of the battery cell are input into a preset battery abnormality recognition model to obtain a recognition result; when the recognition result is an abnormal behavior, a battery abnormality warning is issued.

7. The method according to claim 6, characterized in that Before the step of inputting the average discharge voltage and the average discharge current of the battery cell into a preset battery abnormality recognition model to obtain a recognition result, the method further includes: Acquire historical discharge data of the battery cell, wherein the historical discharge data includes historical discharge voltage and historical discharge current; Annotating the historical discharge data to obtain normal data and abnormal data, wherein the abnormal data is the historical discharge voltage and the historical discharge current corresponding to the abnormal behavior of the battery cell, and the normal data is the data other than the abnormal data in the historical discharge data of the battery cell; Dividing the historical discharge data into a training set and a test set; Using the training set to train the preset model, and using the test set to evaluate the trained preset model; When it is determined that the accuracy of the preset model reaches a preset accuracy threshold, the preset battery abnormality recognition model is obtained.

8. An energy storage management system, characterized in that: The energy storage management system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the energy storage management system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the energy storage management system, the energy storage management system executes the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on an energy storage management system, the energy storage management system is enabled to execute the method according to any one of claims 1 to 7.

Images